LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layer-wise External Attention Network (LEA-Net) for efficient image anomaly detection. The core idea relies on the integration of unsupervised and supervised anomaly detectors via the visual attention mechanism. Our strategy is as follows: (i) Prior knowledge about anomalies is represented as the anomaly map generated by unsupervised learning of normal instances, (ii) The anomaly map is translated to an attention map by the external network, (iii) The attention map is then incorporated into intermediate layers of the anomaly detection network. Notably, this layer-wise external attention can be applied to any CNN model in an end-to-end training manner. For a pilot study, we validate LEA-Net on color anomaly detection tasks. Through extensive experiments on PlantVillage, MVTec AD, and Cloud datasets, we demonstrate that the proposed layer-wise visual attention mechanism consistently boosts anomaly detection performances of an existing CNN model, even on imbalanced datasets. Moreover, we show that our attention mechanism successfully boosts the performance of several CNN models.

Image-based plant disease diagonasis with unsupervised anomaly detection based on reconstructability of colors

This paper proposes an unsupervised anomaly detection technique for image-based plant disease diagnosis. A construction of large and openly available data set on labeled images of healthy and diseased crop plants has led to growing interest in computer vision techniques for automatic plant disease diagnosis. Although supervised image classifiers based on deep learning could be a powerful tool to identify plant diseases, they require huge amount of data sets that have been labeled as healthy and diseased. While, data mining techniques called "anomaly detection" include unsupervised approaches that not require rare samples for training classifiers. The proposed method in this study focuses on the reconstructability of colors on plant images. We expect that a deep encoder decoder network trained for reconstructing colors of healthy plant images certainly fails to reconstruct colors of symptomatic regions. The main contributions of this work are as follows: (i) we propose a new image-based plant disease detection framework utilizing a conditional adversarial network called pix2pix, (ii) we introduce a new anomaly score based on CIEDE2000 color difference. Through experiments using PlantVillage dataset, we demonstrate that our method is superior to an existing anomaly detector called AnoGAN for identifying diseased crop images in terms of accuracy, interpretability and computational efficiency.